作者
Yoshua Bengio
Machine Learning
Learning Independent Features with Adversarial Nets for Non-linear ICA
Comments A preliminary version of this work was presented at the ICML 2017 workshop on implicit models
Improving speech recognition by revising gated recurrent units
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
Comments David Krueger and Tegan Maharaj contributed equally to this work
Independently Controllable Factors
Image Segmentation by Iterative Inference from Conditional Score Estimation
Count-ception: Counting by Fully Convolutional Redundant Counting
Comments Under Review
Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
Comments INTERSPEECH 2017
Multiscale sequence modeling with a learned dictionary
A Closer Look at Memorization in Deep Networks
Comments Appears in Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, and David Krueger contributed equally to this work
Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder
Comments Accepted to Rep4NLP 2017 Workshop at ACL 2017 Conference
Deep Learning for Patient-Specific Kidney Graft Survival Analysis
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
Comments CVPR camera-ready
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
Batch-normalized joint training for DNN-based distant speech recognition
Comments arXiv admin note: text overlap with arXiv:1703.08002
A network of deep neural networks for distant speech recognition
Independently Controllable Features
Comments RLDM submission
Diet Networks: Thin Parameters for Fat Genomics
Journal ref ICLR 2017
Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
Comments 13 pages, 3 figures
A Structured Self-attentive Sentence Embedding
Comments 15 pages with appendix, 7 figures, 4 tables. Conference paper in 5th International Conference on Learning Representations (ICLR 2017)
Hierarchical Multiscale Recurrent Neural Networks
An Actor-Critic Algorithm for Sequence Prediction
A Robust Adaptive Stochastic Gradient Method for Deep Learning
Comments IJCNN 2017 Accepted Paper, An extension of our paper, "ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient"
Mode Regularized Generative Adversarial Networks
Comments Published as a conference paper at ICLR 2017
A Neural Knowledge Language Model
Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
Comments 11 pages, 3 figures
Recurrent Neural Networks With Limited Numerical Precision
Comments NIPS 2016 EMDNN Workshop paper, condensed version of arXiv:1608.06902
Recurrent Neural Networks With Limited Numerical Precision
Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Comments Published as a conference paper at ICLR 2017
